Detection of buried targets via active selection of labeled data: Application to sensing subsurface UXO

When sensing subsurface targets, such as landmines and unexploded ordnance (UXO), the target signatures are typically a strong function of environmental and historical circumstances. Consequently, it is difficult to constitute a universal training set for design of detection or classification algorithms. In this paper, we develop an efficient procedure by which information-theoretic concepts are used to design the basis functions and training set, directly from the site-specific measured data. Specifically, assume that measured data (e.g., induction and/or magnetometer) are available from a given site, unlabeled in the sense that it is not known a priori whether a given signature is associated with a target or clutter. For N signatures, the data may be expressed as {x χ, yχi}χi= 1,N, where x χi is the measured data for buried object χi, and y χi is the associated unknown binary label (target/nontarget). Let the N xχi define the set X. The algorithm works in four steps: 1) the Fisher information matrix is used to select a set of basis functions for the kernel-based algorithm, this step defining a set of n signatures Bn ⊂ X that are most informative in characterizing the signature distribution of the site; 2) the Fisher information matrix is used again to define a small subset Xs ⊂ X, composed of those Xχi for which knowledge of the associated labels y χi would be most informative in defining the weights for the basis functions in Bn; 3) the buried objects associated with the signatures in Xs are excavated, yielding the associated labels y χi, represented by the set Ys; and 4) using B n,Xs, and Ys, a kernel-based classifier is designed for use in classifying all remaining buried objects. This framework is discussed in detail, with example results presented for an actual buried-UXO site.